Merge branch 'net-ntb_netdev-fix-tx-completion-and-error-handling'

Koichiro Den says:

====================
net: ntb_netdev: Fix TX completion and error handling

This small series fixes several TX buffer ownership and queue handling
bugs in ntb_netdev and ntb_transport.

Patch 4 first appeared in my "NTB: Add direct TX/RX using PCI endpoint
DMA" series. Sashiko later reported the same pre-existing leak while
reviewing another series, so I moved the fix here. See:
https://lore.kernel.org/r/20260815032932.151F11F000E9@smtp.kernel.org/

The ntb_transport fixes affect buffer ownership and queue handling in
ntb_netdev, the only in-tree ntb_transport_client implementation, so the
patches need to go in together. I am targeting the net tree for the
series.
====================

Link: https://patch.msgid.link/20260817053519.4135287-1-den@valinux.co.jp
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

2 files changed, 37 insertions, 28 deletions

diff --git a/drivers/net/ntb_netdev.c b/drivers/net/ntb_netdev.c
index 029a4a532a10..02b35cf53a62 100644
--- a/drivers/net/ntb_netdev.c
+++ b/drivers/net/ntb_netdev.c
@@ -199,8 +199,10 @@ static int __ntb_netdev_maybe_stop_tx(struct net_device *netdev,
 static int ntb_netdev_maybe_stop_tx(struct net_device *ndev,
 				    struct ntb_netdev_queue *q, int size)
 {
-	if (__netif_subqueue_stopped(ndev, q->qid) ||
-	    (ntb_transport_tx_free_entry(q->qp) >= size))
+	if (__netif_subqueue_stopped(ndev, q->qid))
+		return -EBUSY;
+
+	if (ntb_transport_tx_free_entry(q->qp) >= size)
 		return 0;
 
 	return __ntb_netdev_maybe_stop_tx(ndev, q, size);
@@ -256,21 +258,30 @@ static netdev_tx_t ntb_netdev_start_xmit(struct sk_buff *skb,
 
 	q = &dev->queues[qid];
 
-	ntb_netdev_maybe_stop_tx(ndev, q, tx_stop);
+	if (unlikely(ntb_netdev_maybe_stop_tx(ndev, q, tx_stop)))
+		return NETDEV_TX_BUSY;
 
 	rc = ntb_transport_tx_enqueue(q->qp, skb, skb->data, skb->len);
-	if (rc)
-		goto err;
+	if (rc) {
+		if (rc == -EAGAIN || rc == -EBUSY) {
+			netif_stop_subqueue(ndev, q->qid);
+			mod_timer(&q->tx_timer,
+				  jiffies + usecs_to_jiffies(tx_time));
+			return NETDEV_TX_BUSY;
+		}
+
+		goto drop;
+	}
 
 	/* check for next submit */
 	ntb_netdev_maybe_stop_tx(ndev, q, tx_stop);
 
 	return NETDEV_TX_OK;
 
-err:
+drop:
+	dev_kfree_skb_any(skb);
 	ndev->stats.tx_dropped++;
-	ndev->stats.tx_errors++;
-	return NETDEV_TX_BUSY;
+	return NETDEV_TX_OK;
 }
 
 static void ntb_netdev_tx_timer(struct timer_list *t)
diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c
index f59f926d4bfa..f9caa1a653c5 100644
--- a/drivers/ntb/ntb_transport.c
+++ b/drivers/ntb/ntb_transport.c
@@ -1719,9 +1719,16 @@ static void ntb_transport_rxc_db(unsigned long data)
 static void ntb_tx_copy_callback(void *data,
 				 const struct dmaengine_result *res)
 {
+	struct ntb_payload_header __iomem *hdr;
 	struct ntb_queue_entry *entry = data;
-	struct ntb_transport_qp *qp = entry->qp;
-	struct ntb_payload_header __iomem *hdr = entry->tx_hdr;
+	struct ntb_transport_qp *qp;
+	unsigned int len;
+	void *cb_data;
+
+	qp = entry->qp;
+	hdr = entry->tx_hdr;
+	cb_data = entry->cb_data;
+	len = entry->len;
 
 	/* we need to check DMA results if we are using DMA */
 	if (res) {
@@ -1768,15 +1775,13 @@ static void ntb_tx_copy_callback(void *data,
 	 * "link down" or similar.  Since no payload is being sent in these
 	 * cases, there is nothing to add to the completion queue.
 	 */
-	if (entry->len > 0) {
-		qp->tx_bytes += entry->len;
-
-		if (qp->tx_handler)
-			qp->tx_handler(qp, qp->cb_data, entry->cb_data,
-				       entry->len);
-	}
+	if (len > 0)
+		qp->tx_bytes += len;
 
 	ntb_list_add(&qp->ntb_tx_free_q_lock, &entry->entry, &qp->tx_free_q);
+
+	if (len > 0 && qp->tx_handler)
+		qp->tx_handler(qp, qp->cb_data, cb_data, len);
 }
 
 static void ntb_memcpy_tx_on_stack(struct ntb_queue_entry *entry, void __iomem *offset)
@@ -1950,15 +1955,6 @@ static int ntb_process_tx(struct ntb_transport_qp *qp,
 		return -EAGAIN;
 	}
 
-	if (entry->len > qp->tx_max_frame - sizeof(struct ntb_payload_header)) {
-		if (qp->tx_handler)
-			qp->tx_handler(qp, qp->cb_data, NULL, -EIO);
-
-		ntb_list_add(&qp->ntb_tx_free_q_lock, &entry->entry,
-			     &qp->tx_free_q);
-		return 0;
-	}
-
 	ntb_async_tx(qp, entry);
 
 	qp->tx_pkts++;
@@ -2348,9 +2344,11 @@ int ntb_transport_tx_enqueue(struct ntb_transport_qp *qp, void *cb, void *data,
 	if (!qp || !len)
 		return -EINVAL;
 
-	/* If the qp link is down already, just ignore. */
 	if (!qp->link_is_up)
-		return 0;
+		return -ENOLINK;
+
+	if (len > qp->tx_max_frame - sizeof(struct ntb_payload_header))
+		return -EMSGSIZE;
 
 	entry = ntb_list_rm(&qp->ntb_tx_free_q_lock, &qp->tx_free_q);
 	if (!entry) {